public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
//ExtractText(pdfStripper, pdfDocument,
// string.Format(@"c:\Users\tri.hoang\Desktop\temp\epub-belastingblad\2014-08\pdf\page_{0}.txt", i.ToString().PadLeft(5, '0')));
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
/// <summary>
/// 读取
/// </summary>
/// <param name="file"></param>
/// <returns></returns>
public string Read(IFormFile file)
{
/*var ss = Directory.GetCurrentDirectory();//获取项目路径
* var st = _hostingEnvironment.ContentRootPath;//获取项目路径
* var fileDir = ss+"\\pdf";
* if (Directory.Exists(fileDir))
* {
* Directory.Delete(fileDir,true);
* }
* Directory.CreateDirectory(fileDir);
* //string fileName = file.FileName;
* //string filePath= fileDir + $@"\{fileName}";
* var fileName = DateTime.Now.ToString("yyyyMMddHHmmss") +
* Path.GetExtension(file.FileName);
* var filePath = Path.Combine(fileDir, fileName);
* using (FileStream fs = System.IO.File.Create(filePath))
* {
* file.CopyTo(fs);
* fs.Flush();
* }
* var files = new FileInfo(filePath);*/
// string currentDirectory = Path.GetDirectoryName((new PdfController()).GetType().Assembly.Location);
PDDocument doc = PDDocument.load(@"G:/Read.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
return(text);
}
/**
* 提取部分页面文本
* @param file pdf文档路径
* @param startPage 开始页数
* @param endPage 结束页数
*/
public static string ExtractTXT(String file, int startPage, int endPage)
{
String content = string.Empty;
try
{
PDDocument document = PDDocument.load(file);
//获取一个PDFTextStripper文本剥离对象
PDFTextStripper stripper = new PDFTextStripper();
// 设置按顺序输出
stripper.setSortByPosition(true);
// 设置起始页
stripper.setStartPage(startPage);
// 设置结束页
stripper.setEndPage(endPage);
//获取文本内容
content = stripper.getText(document);
document.close();
}
catch (java.io.FileNotFoundException ex)
{
}
catch (java.io.IOException ex)
{
}
return(content);
}
public string PdfToText()
{
string pdfText = String.Empty;
PDFParser parser = new PDFParser(new BufferedInputStream(new FileInputStream(PdfFile)));
parser.parse();
PDDocument originialPdfDoc = parser.getPDDocument();
bool isOriginalDocEncrypted = originialPdfDoc.isEncrypted();
if (isOriginalDocEncrypted)
{
originialPdfDoc.openProtection(new StandardDecryptionMaterial(PdfPassword));
}
PDFTextStripper stripper = new PDFTextStripper();
try
{
pdfText = stripper.getText(originialPdfDoc);
}
catch (java.io.IOException ex)
{
throw ex;
}
return(pdfText);
}
/// <summary>
/// Method for extracting PDF data
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public string ExtractTextFromPdf(string filename)
{
String text = "";
try{
if (checkFileExists(filename))
{
_log.Info(filename + "exists in the download folder");
PDDocument doc = null;
try{
doc = PDDocument.load(getPDFFilePath(filename));
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(doc);
}
catch (Exception e) {
_log.Info("Exception in Extracting data from file " + filename + ".pdf" + e.StackTrace);
_log.Info("Exception in Extracting data from file " + filename + ".pdf" + e.StackTrace);
}
finally{
if (doc != null)
{
doc.close();
}
}
}
else
{
Assert.Fail("PDF file not found in 'Downloads' folder.");
}
}
catch (Exception e) {
_log.Info("Exception in extracting text from PDF: " + e.Message);
}
return(text);
}
protected internal String ConvertPDFToDoc(string PDFpath)
{
try
{
PDDocument PDFdoc = null;
PDFTextStripper textstrip = new PDFTextStripper();
String StringDocx = String.Empty;
String DocxPath = String.Empty;
PDFdoc = PDDocument.load(PDFpath);
StringDocx = textstrip.getText(PDFdoc);
PDFdoc.close(); //cierra el pdf
///DocxPath = fn.CreateFolderToSaveDocs(fn.GenerateName()); ///genera la ruta para guardar el archivo.
DocxPath = fn.CreateFolderToSaveDocs(fileName); ///genera la ruta para guardar el archivo.
var wordDoc = DocX.Create(DocxPath);
wordDoc.InsertParagraph(StringDocx);
wordDoc.Save();
////Process.Start("winword.exe", DocxPath);
return(DocxPath);
}
catch (Exception)
{
return("");
}
}
public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
var text = " ";
try
{
text = stripper.getText(doc);
return(text);
}
catch (UnauthorizedAccessException e)
{
MessageBox.Show("Невозможно скопировать текст из Пдф " + PDFFilePath + ". " + e.Message, "Сообщение об ошибке");
return("");
}
catch (FileLoadException FLe)
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". " + FLe.Message, "Сообщение об ошибке");
return("");
}
catch when(text == "")
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". ", "Сообщение об ошибке");
return("");
}
finally
{
doc.close();
}
}
public string parseUsingPDFBox(string input)
{
PDDocument doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
public void ExtractText(string inpufFileName, string outputFileName)
{
#if false
IFilterTextReader.FilterReader reader = new FilterReader(inpufFileName);
var data = reader.ReadToEnd();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(data);
}
#else
PDDocument doc = null;
try
{
doc = PDDocument.load(inpufFileName);
PDFTextStripper stripper = new PDFTextStripper();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(stripper.getText(doc));
}
}
finally
{
if (doc != null)
{
doc.close();
}
}
#endif
}
private string GetTextFromPdfFile(string fileName)
{
PDDocument doc = PDDocument.load(fileName);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
/// <summary>
/// Validates the PDF File Downloaded and the text present in the file
/// </summary>
/// <param name="pdfFileName">The folder or filepath.</param>
/// <param name="textToCheck">The text to be validated.</param>
/// <returns>if the text is present or not</returns>
public static bool ExtractAndValidateTextFromPDF(string pdfFileName, string textToCheck)
{
try
{
string result = string.Empty;
bool validateText = false;
PDDocument doc = PDDocument.load(pdfFileName);
PDFTextStripper stripper = new PDFTextStripper();
result = stripper.getText(doc);
doc.close();
if (result.Length != 0)
{
byte[] bytes = Encoding.Default.GetBytes(result.ToString());
string decodedresult = Encoding.UTF8.GetString(bytes);
string outputPDF = decodedresult.Replace(" ", null).Replace("\r", null).Replace("\n", null);
string validationString = textToCheck.Replace(" ", null);
validateText = outputPDF.Contains(validationString);
}
return(validateText);
}
catch (Exception)
{
throw;
}
}
static void Main(string[] args)
{
PDDocument doc = PDDocument.load("lopreacamasa.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
Console.Write(pdfStripper.getText(doc));
}
private void btnShowPDF_Click(object sender, EventArgs e)
{
PDDocument PDF = PDDocument.load(textBox1.Text);
PDFTextStripper stripper = new PDFTextStripper();
richTextBox1.Text = (stripper.getText(PDF));
}
private static void KamilPdfTest(string input)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
// stripper.getText(doc);
Matrix line = stripper.getTextLineMatrix();
// int page_nr = stripper.getCurrentPageNo();
PDPage page = stripper.getCurrentPage();
Matrix line2 = stripper.getTextMatrix();
int char_cnt = stripper.getTotalCharCnt();
string article_start = stripper.getArticleStart();
string article_end = stripper.getArticleEnd();
string pdf = stripper.getText(doc); // wrzuca caly tekst do sringa - dziala
char_cnt = pdf.Length;
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
/// <summary>
/// Get text from the binary using PDFBox
/// </summary>
/// <returns>The text of the binary or null if we could not process the text</returns>
public override string GetTextFromDocumentBinary()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract text from empty bytes for file " + Name);
return(null);
}
try
{
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(doc);
}
catch (Exception e)
{
log.Error("Failed to get the text from the PDF file " + Name, e);
}
return(text);
}
public string parsePDF(string filepath)
{
PDDocument document = PDDocument.load(filepath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(document));
}
public string ParseFile(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
doc.close();
return text;
}
private static string ReadPdf(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
return(text);
}
public static string PdfFileReader(FileInfo fileName)
{
PDDocument doc = PDDocument.load(fileName.FullName);
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
return(text);
}
public string ParseFile(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
doc.close();
return(text);
}
private string convertPdfToTxt(string rootDir)
{
DirectoryInfo root = new DirectoryInfo(rootDir);
FileInfo[] files = root.GetFiles("*.pdf");
if (files.Length == 0)
{
MessageBox.Show("文件夹下不包含pdf文件.");
}
string bakFolderName = rootDir + "\\" + DateTime.Now.ToString("yyyyMMddHHmmss");
DirectoryInfo rootBak = new DirectoryInfo(bakFolderName);
if (!rootBak.Exists)
{
rootBak.Create();
}
SetPbValue(0);
//1.pdf转txt
for (int i = 0; i < files.Length; i++)
{
try
{
SetLableText(string.Format("pdf转txt.已处理{0},共{1},完成比例:{2}%", i + 1, files.Length, decimal.Round((Convert.ToDecimal(i + 1) / Convert.ToDecimal(files.Length) * 100), 2).ToString()), lblInfo);
SetPbValue((int)decimal.Round((Convert.ToDecimal(i + 1) / Convert.ToDecimal(files.Length) * 100), 2));
FileInfo pdfFile = files[i];
string txtFilePath = bakFolderName + "\\" + pdfFile.Name.Substring(0, pdfFile.Name.Length - 4) + ".txt";
FileInfo txtFile = new FileInfo(txtFilePath);
if (!txtFile.Exists)
{
FileStream stream = txtFile.Create();
stream.Close();
}
PDDocument doc = PDDocument.load(pdfFile.FullName);
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
StreamWriter swPdfChange = new StreamWriter(txtFile.FullName, false, Encoding.GetEncoding("gb2312"));
swPdfChange.Write(text);
swPdfChange.Close();
}
catch (Exception)
{
continue;
}
}
//this.txtTxtFolder.Text = bakFolderName;
this.SetLableText(bakFolderName, txtTxtFolder);
return(bakFolderName);
}
public static String[] PdfToText(string path)
{
PDDocument doc = PDDocument.load(path);
PDFTextStripper pdfStripper = new PDFTextStripper();
var text = pdfStripper.getText(doc).Split('\r');
return(text);
}
private void button2_Click(object sender, EventArgs e)
{
PDDocument doc = PDDocument.load(textBox1.Text);
PDFTextStripper striper = new PDFTextStripper();
richTextBox1.Text = (striper.getText(doc));
speechsynth.SelectVoiceByHints(VoiceGender.Female);
speechsynth.SpeakAsync("" + richTextBox1.Text);
}
/**
* string getFilePath(string path)
* {
* // Specify the path to save the uploaded file to.
* string savePath = "C:\\Users\\DR.AKUL\\Documents\\Visual Studio 2010\\Projects\\PlagijatorFinder\\PlagijatorFinder\\uploadFiles\\";
*
* // Get the name of the file to upload.
* string fileName = FileUpload1.FileName;
*
* // Create the path and file name to check for duplicates.
* path = savePath + fileName + ".txt";
* return path;
* }
**/
private static string parseUsingPDFBox(string filename)
{
PDDocument doc = PDDocument.load(filename);
PDFTextStripper stripper = new PDFTextStripper();
string text = stripper.getText(doc);
doc.close();
return(text);
}
private void button_Click(object sender, RoutedEventArgs e)
{
PDDocument doc = null;
Mouse.OverrideCursor = Cursors.Wait;
try
{
doc = PDDocument.load(Properties.Settings.Default.PdfPath);
PDFTextStripper stripper = new PDFTextStripper();
string data = stripper.getText(doc);
MatchCollection match = Regex.Matches(data, "FA\\d{8}", RegexOptions.IgnoreCase);
if (match.Count > 0)
{
try
{
XmlDocument xml = new XmlDocument();
xml.Load(this.filePath.Text);
xml.Save(this.filePath.Text + ".backup");
var manager = new XmlNamespaceManager(xml.NameTable);
manager.AddNamespace("dat", "http://www.stormware.cz/schema/version_2/data.xsd");
int count = 0;
foreach (var item in match)
{
string request = "/dat:dataPack/dat:dataPackItem[@id=\"" + item + "\"]";
try
{
foreach (XmlNode node in xml.SelectNodes(request, manager))
{
node.ParentNode.RemoveChild(node);
count++;
}
}
catch (Exception ex)
{
}
}
xml.Save(this.filePath.Text);
MessageBox.Show("Erased " + count + " items.");
}
catch (Exception ex)
{
MessageBox.Show(ex.Message + "\nPlease check request XPath syntax.", "Error", MessageBoxButton.OK);
}
}
}
finally
{
if (doc != null)
{
doc.close();
}
}
Mouse.OverrideCursor = null;
}
static private string[] PDFToTextPDFBox(string file, string[] split, StringSplitOptions option)
{
string pdftext = string.Empty;
PDDocument doc = PDDocument.load(file);
PDFTextStripper stripper = new PDFTextStripper();
pdftext = stripper.getText(doc);
doc.close();
return(pdftext.Split(split, option));
}
public string ExtractTextFromPdf(string filePath)
{
var doc = PDDocument.load(fullFilePath);
//PSEDocument pd = new PSEDocument();
var stripper = new PDFTextStripper();
string pdfText = stripper.getText(doc).TrimEnd();
return(pdfText);
}
public void TestReaderLastLine()
{
var stripper = new PDFTextStripper();
var reader = new PSEReportReader(stripper.getText(doc).TrimEnd());
string expected = "*** Grand total includes main,oddlot and block sale transactions";
string actual = reader.PSEReportString[reader.PSEReportString.Count - 1].Trim();
Assert.AreEqual(expected, actual);
}
string get_text_from_pdf_by_pdfbox(string path)
{
PDDocument pdffile = PDDocument.load(new java.io.File(path));
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(pdffile);
pdffile.close();
//File.WriteAllText(dst, text, Encoding.GetEncoding("GBK"));
return(text);
}
public string GetStringFromPdfStream(Stream stream)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(new JavaIoWrapper(stream));
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(doc);
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
/// <summary>
/// Parses a pdf item and returns its content as string.
/// </summary>
/// <param name="mediaItem">MediaItem (should be a pdf - otherwise an empty string will be returned).</param>
/// <returns>String represantation of the pdf content.</returns>
public static string ParsePdf(MediaItem mediaItem)
{
if (mediaItem.MimeType != PdfMimetype) return string.Empty;
PDDocument doc = null;
ikvm.io.InputStreamWrapper wrapper = null;
try
{
var stream = mediaItem.GetMediaStream();
wrapper = new ikvm.io.InputStreamWrapper(stream);
doc = PDDocument.load(wrapper);
if (doc.isEncrypted())
{
string[] pwArray = LoadPasswords();
doc = Decrypt(doc, pwArray);
if (doc == null)
{
Log.Warn("PdfUtil :: ParsePDF :: Decryption Failed for: [" + mediaItem.Name + "]", typeof(PdfUtil));
return string.Empty;
}
else
{
Log.Debug("PdfUtil :: ParsePDF :: Successfully decrypted [" + mediaItem.Name + "]", typeof(PdfUtil));
}
}
var stripper = new PDFTextStripper();
return stripper.getText(doc);
}
catch (Exception ex)
{
Log.Error("PdfUtil :: ParsePDF :: Error parsing pdf: [" + mediaItem.Name + "]", ex);
return string.Empty;
}
finally
{
if (doc != null)
{
doc.close();
wrapper.close();
}
}
}
/// <summary>
/// Converts the PDF files to text files.
/// </summary>
public static void ConvertPDFFilesToTextFiles()
{
//Only convert PDF files
var pdfFilesToConvert = Directory.GetFiles(FolderLocation).Where(f => f.Contains(".pdf")).ToList();
var txtFilesArray = pdfFilesToConvert.Where(f => f.Contains(".txt")).ToArray();
//Remove PDF files that already have text files
pdfFilesToConvert.RemoveAll(pdfFile => txtFilesArray.Contains(pdfFile.Replace(".pdf", ".txt")));
//For testing, only do 1
//pdfFilesToConvert.RemoveRange(1, files.Count - 1);
//Parallelize the PDF conversion
pdfFilesToConvert.AsParallel().ForAll(filePath =>
{
var doc = PDDocument.load(filePath);
var pdfStripper = new PDFTextStripper();
var text = pdfStripper.getText(doc);
File.WriteAllText(filePath.Replace(".pdf", ".txt"), text);
});
}
public Task<bool> Process(ICrawler crawler, PropertyBag propertyBag)
{
if (propertyBag.StatusCode != HttpStatusCode.OK
|| propertyBag.Response == null)
{
return Task.FromResult(true);
}
PDDocument doc = null;
try
{
doc = PDDocument.load(new ByteArrayInputStream(propertyBag.Response));
PDFTextStripper stripper = new PDFTextStripper();
propertyBag.Text = stripper.getText(doc);
}
finally
{
doc?.close();
}
return Task.FromResult(true);
}
public string Parse(string fileName)
{
//Load in file. Using java.io because pdfbox is ported from java.
var pdfFile = new FileInputStream(fileName);
//Load file into the pdf parser
var pdfParser = new PDFParser(pdfFile);
//Parse the document, so that we can get it for the COSDocument
pdfParser.parse();
/*
COSDocument is the in-memory representation of the PDF.
see https://pdfbox.apache.org/docs/1.8.4/javadocs/org/apache/pdfbox/cos/COSDocument.html
*/
var cosDocument = pdfParser.getDocument();
var pdDocument = new PDDocument(cosDocument);
//Instantiate text stripper.
var pdfTextStripper = new PDFTextStripper();
/* Needed for only stripping specific pages
pdfTextStripper.setStartPage(0);
pdfTextStripper.setEndPage(pdDocument.getNumberOfPages());
*/
//Needed so that we can close the pdDocument before returning from this method
var strippedText = pdfTextStripper.getText(pdDocument);
//This closes all storage and delete the tmp files.
pdDocument.close();
cosDocument.close();
return strippedText;
}
private ResultISBN parseISBNwithPDFBox(string filename)
{
try
{
PDDocument doc = PDDocument.load(filename);
PDFTextStripper stripper = new PDFTextStripper();
// Split the search into parts (no need to search 10 pages
// if the result is on the thrid
stripper.setStartPage(0);
stripper.setEndPage(3);
string rezultat = stripper.getText(doc);
string isbn = (new ISBN()).getISBNFromContent(rezultat);
if (isbn != null) return (new ResultISBN(isbn, rezultat));
stripper = new PDFTextStripper();
stripper.setStartPage(3);
stripper.setEndPage(7);
rezultat = stripper.getText(doc);
isbn = (new ISBN()).getISBNFromContent(rezultat);
if (isbn != null) return (new ResultISBN(isbn, rezultat));
stripper = new PDFTextStripper();
stripper.setStartPage(7);
stripper.setEndPage(10);
rezultat = stripper.getText(doc);
isbn = (new ISBN()).getISBNFromContent(rezultat);
if (isbn != null) return (new ResultISBN(isbn, rezultat));
return (new ResultISBN(null, null));
}
catch (Exception e)
{
// MessageBox.Show(e.Message);
File.AppendAllText("log_Parser.txt", DateTime.Now.ToShortDateString() + " " + DateTime.Now.ToShortTimeString() + ": " + e.Message+" "+filename + Environment.NewLine);
return (new ResultISBN(null, null));
}
}
public string parsePDF(string filepath)
{
PDDocument document = PDDocument.load(filepath);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(document);
}
private void worker_DoWork(object sender, DoWorkEventArgs e)
{
try
{
PDDocument doc = PDDocument.load(_fileName);
EmptyMethod step = StepForm;
if (step != null)
{
form.Invoke(step);
}
PDFTextStripper stripper = new PDFTextStripper();
_result = stripper.getText(doc);
_success = true;
}
catch
{
_success = false;
}
finally
{
EmptyMethod hide = HideForm;
if (hide != null)
{
form.Invoke(hide);
}
}
}
public override string ReadToEnd()
{
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(document);
}
public string ReadDocument()
{
PDFTextStripper pdfTextStripper = new PDFTextStripper();
return pdfTextStripper.getText(_pdfDocument);
}
private string GetTextFromPdfFile(string fileName)
{
PDDocument doc = PDDocument.load(fileName);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(doc);
}
private static string ExtractTextFromPdf(string path)
{
PDDocument doc = null;
try {
doc = PDDocument.load(path);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(doc);
}
finally {
if (doc != null) {
doc.close();
}
}
}
private void parsePDF()
{
PDDocument doc = PDDocument.load("2.pdf");
PDFTextStripper stripper = new PDFTextStripper();
//stripper.setSortByPosition(true);
string text = stripper.getText(doc);
stripper.getSeparateByBeads();
stripper.getTextLineMatrix();
Regex regex = new Regex("Сокращенное наименование (.*)\"", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var orgName = regex.Match(text).Groups[1].Value;
regex = new Regex("ИНН (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var inn = regex.Match(text).Groups[1].Value;
regex = new Regex("КПП (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var kpp = regex.Match(text).Groups[1].Value;
regex = new Regex("Должность (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var post = regex.Match(text).Groups[1].Value;
regex = new Regex("Фамилия (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var lastName = regex.Match(text).Groups[1].Value;
regex = new Regex("Имя (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var firstName = regex.Match(text).Groups[1].Value;
regex = new Regex("Отчество (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var surName = regex.Match(text).Groups[1].Value;
regex = new Regex("ОГРН (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var ogrn = regex.Match(text).Groups[1].Value;
regex = new Regex("Почтовый индекс (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var postIndex = regex.Match(text).Groups[1].Value;
regex = new Regex("Субъект Российской Федерации (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var city = regex.Match(text).Groups[1].Value;
regex = new Regex("Улица /(проспект, переулок и т.д./) (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var street = regex.Match(text).Groups[1].Value;
regex = new Regex("Дом /(владение и т.п./) (.*)(\n[^0-9])?.*\r", RegexOptions.Multiline | RegexOptions.IgnoreCase);
var house = regex.Match(text).Groups[1].Value;
textBox4.Text = text;
textBox3.Text = orgName + " / " +inn + " / " +kpp + " / " +post + " / " +lastName + " / " +firstName + " / " +surName +" / " + ogrn + " / " + postIndex + " / "+ city +" / "+street+" / "+house;
//textBox3.Text = match[0].ToString();
//string[] lines = text.Split(new string[] { "\r?\n" }, StringSplitOptions.None); // give you all the lines separated by new line
//string[] cols = lines[0].Split(new string[] { "\\s+ " }, StringSplitOptions.None); // gives array separated by whitespaces
//textBox3.Text = cols[0].ToString();
//return stripper.getText(doc);
}
//This method parses the pdf and returns a string with text content
public static string ParseUsingPdfBox(string filename)
{
PDDocument doc;
try
{
doc = PDDocument.load(filename);
}
catch
{
return null;
}
var sb = new StringBuilder();
var stripper = new PDFTextStripper();
var lastPage = stripper.getEndPage();
var lastPageMinus10 = lastPage - 10;
stripper.setStartPage(1);
stripper.setEndPage(10);
string temp = stripper.getText(doc);
sb.Append(temp);
stripper.setStartPage(lastPageMinus10);
stripper.setEndPage(lastPage);
temp = stripper.getText(doc);
sb.Append(temp);
doc.close();
return sb.ToString();
}
private static string ParseUsingPDFBox(string inputFile, string outputFile)
{
var doc = PDDocument.load(inputFile);
var stripper = new PDFTextStripper();
var result = stripper.getText(doc);
if (string.IsNullOrEmpty(outputFile))
return result;
using (var sw = new StreamWriter(outputFile))
{
sw.WriteLine(result);
}
return string.Empty;
}
private static string parseUsingPDFBox(string filename)
{
PDDocument doc = PDDocument.load(@filename);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(doc);
}
